Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Moonshot AI’s open‑weights model Kimi K2.6 won the Word Gem Puzzle contest with 22 match points (7‑1‑0), beating all Western LLMs.
- Xiaomi’s MiMo V2‑Pro placed second, narrowly trailing the Chinese winner.
- OpenAI’s GPT‑5.5 came in third, showing a gap behind Chinese models.
- Anthropic’s Claude Opus 4.7 finished fifth, lower than expected.
- Zhipu AI’s GLM 5.1 landed fourth, out‑performing other Western labs.
Why it matters: Moonshot AI gains credibility and likely enterprise contracts, while Western labs see a dip in perceived leadership; the open‑weights win will boost Chinese AI exports and force proprietary LLM providers to cut prices.
